© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10666
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations related to medical processes, technologies, and manufacturers.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.89
    WebVitals
    -0.85
     HttpNotFound
    -0.76
     Мексичка
    -0.75
    UrlResolution
    -0.73
    InstanceState
    -0.73
    titleMargin
    -0.73
    fjspx
    -0.69
     initComponents
    -0.69
     Drapeau
    -0.68
    POSITIVE LOGITS
    Check
    0.65
    X
    0.64
     stället
    0.62
    T
    0.60
     varandra
    0.57
    Search
    0.57
    Map
    0.57
     skydd
    0.56
     gånger
    0.56
    C
    0.55
    Activations Density 8.886%

    No Known Activations